The collapsed example only sent --missing-content, so substituting
--rating good violated the valuable-sources requirement and the
--silent call swallowed the HTTP 400, silently losing the refund.
Show both --valuable-sources and --missing-content so any rating
substitution satisfies the substantive-content rule.
A live --rating good default anchors copy-paste agents toward
reporting good and skews the feedback signal. Show a
<good|partial|bad> placeholder that cannot run until the agent
chooses, keep the rating-neutral --missing-content field as the
worked example, and let the rules list govern per-rating required
fields. Applied to both mirrored snippets.
Replace the three parallel rating examples (latterly commented
alternates) with a single guarded good-rating call. The rules list
above already defines per-rating field requirements and the
--missing-content section documents payload shapes, so the extra
examples duplicated both. Follows the default-with-escape-hatch
pattern and matches the mirrored firecrawl skill snippet.
All three rating calls were live sequential commands inside the guard,
so a literal copy-paste submitted three conflicting ratings for one
search id. Keep the good-rating call live and show partial/bad as
commented alternates, matching the "send exactly one" prose.
Update the .claude-plugin skill paths missed by the folder rename, and
move the three search-feedback examples inside the guard conditional so
copying any of them cannot bypass the zero-result check.
The installer copies each skill to ~/.agents/skills/<frontmatter-name>/,
and the router skill is named "firecrawl", so ../firecrawl-cli/SKILL.md
links 404ed after install. Rename the folder to skills/firecrawl/ so the
folder and frontmatter agree and cross-skill links resolve both in-repo
and installed.
A bare SEARCH_ID=$(jq -er ...) assignment does not stop the follow-on
search-feedback call when the guard fails (missing file or zero
results), so it fired with an empty id. Wrap the feedback call in the
guard conditional in both mirrored snippets.
Adversarial review against src/ surfaced wrong claims that survived the
first audit pass, in the same files this PR touches:
- scrape: -H is --html (raw HTML shortcut), not HTTP headers
- interact: --language does not exist; the CLI uses --node/--python/--bash
- download: the command is only registered as 'firecrawl x download'
(experimental), so all examples used a nonexistent invocation; the
'only these options' list omitted --lockdown; the wizard example is
TTY-only and blocks agents without -y
- search: spell out guard-failure behavior and split the missing-file
vs stale-file hazards
- scrape/agent: reword confusing multi-URL parenthetical and dedupe the
--wait tip
- cli: mirror the guarded jq search-id recipe so it doesn't drift from
the corrected search skill
Make download examples safe for non-interactive flows and correct agent JSON guidance in the README. Include skill Markdown in Prettier scripts so formatting drift is caught.
* fix(research): describe the real paper corpus in CLI help
Why: over 40 agent traces, 8/8 biomedical CLI runs read the root-help
research line ("Research arXiv papers and GitHub history"), concluded the
index was arXiv-only, and hand-scraped PubMed instead of ever running
`firecrawl research`. The index is ~43M abstracts, ~90% biomedical. The
group description is the single highest-leverage string: it renders both
in `firecrawl --help` and as the `firecrawl research --help` header.
Summary:
- research group description now names the corpus (PubMed/bioRxiv/medRxiv
plus arXiv), its scale, and routes agents away from hand-scraping.
- search-papers description drops the three "arXiv" claims and names the
multi-source id forms it actually returns; keeps the load-bearing
"run several distinct framings" guidance verbatim.
- search-papers --categories only claims what is true: arXiv-style
taxonomy labels, not applicable to biomedical records.
- search --categories disambiguates `research` (a ~web-domain filter)
from the paper index, pointing at `research search-papers`. The wire
value 'research' is unchanged.
- related-papers accepts pmid:/pmcid:/doi:/arxiv: forms in its docs, in
line with inspect-paper and read-paper.
- research examples now include biomedical ids, not arXiv only.
- cli-argv tests gain the research pair that mirrored `developer`, plus a
regression guard that root help names the biomedical corpus.
* docs(readme): route paper search to `research`, add its command section
Why: the README taught the wrong tool. "# Find research papers" was
followed by `firecrawl search --categories research`, which is only a
website filter over ordinary web results, not the paper index. README
also had a `###` section for every command except `research`, so the
index had no documentation surface at all, and the tagline omitted both
`research` and `developer`.
Summary:
- the "Find research papers" example now leads with `research
search-papers`; the `--categories research` example stays but is
labelled as the website filter it is.
- same disambiguation added to the category example block and the search
options table.
- new `### research` section beside `developer`: corpus and scale, the
explicit "not the same as --categories research" note, all five
subcommands, search-papers options, and workflow tips.
- line-3 tagline now mentions research papers and developer sources.
* chore: add research vocabulary to package metadata, bump to 1.20.0
Why: npm search and package listings carried no research, paper, or
biomedical vocabulary, so the paper index was undiscoverable from outside
the CLI too. Behavioural metadata change across help text, docs, and
skills -> minor bump.
Summary:
- package.json description names the paper index and its sources.
- keywords gain research, paper/literature search, biomedical, pubmed,
biorxiv, medrxiv, arxiv, life sciences.
- 1.19.31 -> 1.20.0.
- nfpm.yaml and homebrew/firecrawl-cli.rb carry the same one-line
description; both updated. The brew `desc` is kept under the 80-char
audit limit.
Note: homebrew/firecrawl-cli.rb `version` is 1.10.0 and is not written by
any release tooling in this repo; left as found rather than guessed at.
* docs(skills): give paper search a routing surface in the CLI skills
Why: agents load skills before they load `--help`. firecrawl-search had a
full "Developer search" section and nothing for research; its options
table listed `research` with no elaboration, so the naming collision with
the paper index was invisible. firecrawl-cli's routing table and "When to
Load References" omitted research entirely, so nothing ever pointed an
agent at `firecrawl research`.
Summary:
- firecrawl-search: new "## Paper search" section parallel to "##
Developer search" — states plainly that `--categories research` is not
the paper index, routes to `research search-papers`, and shows the
find/expand/verify loop with real id forms.
- firecrawl-search: `--categories` options row and "When to use" now
disambiguate the two; frontmatter description gains literature triggers
so the skill actually loads on a biomedical task.
- firecrawl-cli: research rows added to the routing table and to "When to
Load References", both stating the anti-pattern (hand-scraping PubMed).
* docs: stop pinning stale CLI versions in install commands
Why: cubic flagged the README install example pinning firecrawl-cli@1.19.6
while this PR ships 1.20.0. The pin was already 25 patches behind npm's
published 1.19.31, and the same stale pin appeared in five more places in
the bundled skills rules.
Summary: install and run commands now use @latest, matching the convention
the public docs already use in all 30 of their occurrences. That removes the
drift permanently rather than trading one stale pin for another — and avoids
pinning 1.20.0, which is not published yet and would break the documented
one-shot install until release. The illustrative `--status` sample output now
shows the version this PR ships.
Test Plan: pnpm test 422/422, prettier clean, no hard-pinned versions remain
in any markdown file.
The developer command called /v2/developer/search. That mount rejects a
keyless caller, so keyless developer search never reached the index. It
is also the path that may be withdrawn. Call /v2/search/developer, the
public path, which accepts a keyless caller.
The API returns 10 results by default, not 20. Correct the help text and
the README.
Release 1.19.27 is on npm, so a publish of the same version fails. This
bump carries --skills-only on the developer command.
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
The developer index now has two surfaces, the same as research: the
`developer` category on `firecrawl search`, and a dedicated command.
The command mirrors the research commands. It calls GET
/v2/developer/search, keeps the keyless free-tier path, and renders the
ranked hits as markdown blocks with the passages clipped at 1200
characters; `--json` keeps the full envelope. It takes a query and
`--limit` only; the endpoint accepts no filters, and that narrow
surface is deliberate.
New tests cover the request URL, the readable and JSON output, and the
error path. Two argv tests prove the command appears in the root help
and parses, so a wrapper cannot drop it the way `executeSearch` once
dropped the category group.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01C4vZ6XH65bUJDkLthyfmvC
`firecrawl search <query> --categories developer` searches an index built
for coding agents: GitHub issues, merged pull requests, repository
READMEs, and curated documentation sites.
The API already served the category. The CLI rejected the value, and
`executeSearch` copied only `web`, `images`, and `news` out of the
payload. A developer group therefore never reached the caller.
The category is an extra arm, not a filter on the web results, so the API
returns its hits in `data.developer`. The command copies that group
through, prints it under its own heading, and labels the web group when
both are present.
A matched passage runs to several KB. The readable output clips it at 500
characters and names `--json`, which keeps the full text. Without the
clip, three hits flood a terminal.
Validated in the Stage-1 final canary: CLI config stores an environment reference, not a literal credential; production MCP compatibility remains green.
Add support for scoping init/setup to a single agent/harness. README documents one-shot usage. scripts/install.sh forwards installer args to `firecrawl init` (non-interactive) and runs `init --yes` when piped. init.ts: add interactive harness picker, detectInstalledAgentNames, and installRepoAcrossAgents to allow routing skills/workflows to a subset of detected agents or a single --agent. skills-native.ts: canonicalize per-agent global skills dirs (fixes several agent paths), add detectInstalledAgentNames helper. This enables one-shot, non-interactive, and interactive per-harness installs.
Research commands bypassed the SDK's typed methods and never set
integration, so requests were logged with integration=NULL. Append
integration=cli as a query param in getResearch, covering all five
subcommands in both keyed and keyless modes. Bump to 1.19.24.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BJ3prpziToFecBhLGRiX6t
Allow monitor create/update to only read piped stdin when flags can't build a payload. Added allowImplicitStdin option to readJsonPayload and exported helpers hasCreateFlagPayload / hasUpdateFlagPayload to detect when flags are sufficient. Updated command actions to pass the allowImplicitStdin flag and extended tests to cover the stdin payload policy. Also bumped package version to 1.19.23.
Max